{
  "markdown": "<!--\n  This README is the SINGLE SOURCE OF TRUTH, maintained in the private monorepo at\n  public_sdk/README.md and synced to the public repo root by scripts/sync_to_public.sh.\n  DO NOT edit the copy in maximem-ai/maximem_synap_sdk directly: changes there are\n  overwritten on the next sync. Edit here instead.\n  The integration table below is generated by scripts/gen_readme_integrations.py.\n-->\n<p align=\"center\">\n  <picture>\n    <source media=\"(prefers-color-scheme: dark)\" srcset=\"assets/banner-light.png\">\n    <source media=\"(prefers-color-scheme: light)\" srcset=\"assets/banner-dark.png\">\n    <img src=\"assets/banner-light.png\" alt=\"Maximem Synap: AI Agents Forget. Synap Makes Them Remember.\" width=\"100%\" />\n  </picture>\n</p>\n\n<p align=\"center\">\n  <a href=\"https://docs.maximem.ai\"><strong>Docs</strong></a> ·\n  <a href=\"https://synap.maximem.ai\"><strong>Dashboard</strong></a> ·\n  <a href=\"https://www.maximem.ai/blog/synap-benchmark-results\"><strong>Benchmarks</strong></a> ·\n  <a href=\"https://www.maximem.ai/synap\"><strong>Website</strong></a>\n</p>\n\n<p align=\"center\">\n  <a href=\"https://pypi.org/project/maximem-synap\"><img src=\"https://img.shields.io/pypi/v/maximem-synap?style=flat-square&color=blue&label=pypi\" alt=\"PyPI\" /></a>\n  <a href=\"https://pypi.org/project/maximem-synap\"><img src=\"https://img.shields.io/pypi/dm/maximem-synap?style=flat-square&color=blue\" alt=\"PyPI Downloads\" /></a>\n  <a href=\"https://www.npmjs.com/package/@maximem/synap-js-sdk\"><img src=\"https://img.shields.io/npm/v/@maximem/synap-js-sdk?style=flat-square&color=blue&label=npm\" alt=\"npm\" /></a>\n  <a href=\"https://pypi.org/project/maximem-synap\"><img src=\"https://img.shields.io/pypi/pyversions/maximem-synap?style=flat-square\" alt=\"Python versions\" /></a>\n  <a href=\"LICENSE\"><img src=\"https://img.shields.io/badge/license-Apache%202.0-blue?style=flat-square\" alt=\"License\" /></a>\n  <a href=\"https://x.com/maximem_ai\"><img src=\"https://img.shields.io/badge/follow-%40maximem__ai-1DA1F2?style=flat-square&logo=x&logoColor=white\" alt=\"Twitter\" /></a>\n  <a href=\"https://www.linkedin.com/company/maximem-ai\"><img src=\"https://img.shields.io/badge/LinkedIn-Maximem%20AI-0A66C2?style=flat-square&logo=linkedin&logoColor=white\" alt=\"LinkedIn\" /></a>\n</p>\n\n---\n\n## The memory layer for production AI agents\n\nYour AI agents forget everything between conversations. Synap fixes that with a production-grade memory layer built for applications that serve real users at scale. **#1 on [LongMemEval](https://www.maximem.ai/blog/synap-benchmark-results) (92%) and [LoCoMo](https://www.maximem.ai/blog/synap-benchmark-results) (93.2%)**, sub-15ms anticipatory retrieval, and native integrations with every major AI framework.\n\n<p align=\"center\">\n  <strong>LangChain · LangGraph · LlamaIndex · CrewAI · AutoGen · Haystack · Google ADK · OpenAI Agents · Semantic Kernel · Pydantic AI · Agno · LiveKit · Pipecat · Claude Agent · Mastra · Vercel AI SDK · NeMo Agent Toolkit · Microsoft Agent Framework</strong>\n</p>\n\n> **What's in this repo:** the open-source Python and JavaScript SDKs plus all framework integrations, licensed under Apache 2.0. The Synap memory engine itself (ingestion, entity resolution, retrieval, anticipation) runs as a fully managed cloud service operated by Maximem and is **not** open source. The SDKs in this repo are clients for that service; there is nothing to self-host, and an [API key](https://www.maximem.ai/synap) is required.\n\n---\n\n## Benchmarks\n\nSynap leads the field on the two standard long-term memory benchmarks, evaluated on identical hardware with an open-source harness.\n\n| Benchmark | Synap accuracy |\n|---|---|\n| **LongMemEval** | **92%** |\n| **LoCoMo** | **93.2%** |\n\nSynap outperforms leading published memory systems, run through the same [open-source evaluation harness](https://github.com/maximem-ai/memory_and_context_eval_harness) on identical hardware and configs.\n\n> **\"Longer conversations make Synap better, not worse.\"** Richer entity graphs and stronger pattern recognition at scale.\n\nFull methodology and reproduction instructions → [maximem.ai/blog/synap-benchmark-results](https://www.maximem.ai/blog/synap-benchmark-results)\n\n---\n\n## Install\n\n```bash\n# Python\npip install maximem-synap\n\n# JavaScript / TypeScript\nnpm install @maximem/synap-js-sdk\n```\n\n---\n\n## 60-second quickstart\n\nYour agent forgets. Synap remembers across conversations, sessions, and devices.\n\nThe SDK connects to the hosted Synap cloud service, so you'll need an [API key](https://www.maximem.ai/synap). There's no local server to run: memory processing happens in Synap's cloud, not in this package.\n\n```python\nimport asyncio\nfrom maximem_synap import MaximemSynapSDK\n\nsdk = MaximemSynapSDK(api_key=\"your-api-key\")\n\nasync def main():\n    await sdk.initialize()\n\n    # Monday's standup\n    await sdk.conversation.record_message(\n        conversation_id=\"mon-standup\",\n        user_id=\"alice\",\n        role=\"user\",\n        content=\"I'm migrating our auth service to OAuth2 this sprint.\",\n    )\n\n    # Friday: completely different conversation, same user\n    context = await sdk.fetch(\n        conversation_id=\"fri-review\",\n        user_id=\"alice\",\n        search_query=[\"what is alice working on?\"],\n    )\n\n    print(context.formatted_context)\n    # → \"Alice is migrating the auth service to OAuth2 this sprint.\"\n\nasyncio.run(main())\n```\n\n<details>\n<summary><strong>JavaScript / TypeScript</strong></summary>\n\n```javascript\nconst { createClient } = require('@maximem/synap-js-sdk');\n\nconst client = createClient({ apiKey: 'your-api-key' });\nawait client.init();\n\n// Record\nawait client.conversation.recordMessage({\n    conversationId: 'mon-standup',\n    userId: 'alice',\n    role: 'user',\n    content: \"I'm migrating our auth service to OAuth2 this sprint.\",\n});\n\n// Fetch later, anywhere\nconst context = await client.fetchUserContext({\n    userId: 'alice',\n    query: 'what is alice working on?',\n});\n\nconsole.log(context.formattedContext);\n```\n\n</details>\n\n---\n\n## What makes Synap different\n\n### 🎯 Anticipatory Retrieval\n\nSynap **pre-fetches context before your agent requests it**. 15ms P50 latency in production. For voice AI agents, this is the difference between natural conversation and awkward pauses.\n\n### 🔗 Entity Resolution\n\nWhen a user says *\"my manager\"* in turn 3 and *\"Sarah\"* in turn 12, Synap resolves them automatically. Cross-session, cross-conversation, without the agent doing any work.\n\n### ⏳ Temporal Awareness\n\nContext from 30 minutes ago and context from 30 days ago should not carry equal weight. Synap applies temporal decay and relevance scoring so your agent surfaces the right information at the right time.\n\n### 🧠 Conscious Forgetting\n\nWhen a user says *\"ignore what I said about the budget,\"* Synap processes that as a retraction, not just more context to store. Contradiction handling is built into the pipeline.\n\n### 🏗️ Custom Memory Architectures\n\nNo universal memory model. Synap builds customized memory architectures per use case. Customer support agents and voice AI agents need different context strategies. Synap handles both.\n\n### 🏢 Multi-Tenant Scoping\n\nBuilt for B2B from day one. Memory is scoped across a four-level hierarchy:\n\n```\nclient          → shared knowledge across your entire platform\n  └── customer  → per-company context (multi-tenant B2B)\n        └── user       → per-user memory and preferences\n              └── conversation → in-session history\n```\n\nOne `fetch()` call merges all relevant scopes in parallel.\n\n---\n\n## Framework integrations\n\nInstallable packages, not code snippets. Deep framework surfaces with callbacks, graph nodes, retrievers, memories, and plugins.\n\n### LangChain\n\n```bash\npip install maximem-synap maximem-synap-langchain\n```\n\n```python\nfrom maximem_synap import MaximemSynapSDK\nfrom synap_langchain import SynapChatMessageHistory\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.runnables.history import RunnableWithMessageHistory\n\nsdk = MaximemSynapSDK(api_key=\"your-api-key\")\nawait sdk.initialize()\n\nchain = RunnableWithMessageHistory(\n    ChatOpenAI(),\n    lambda session_id: SynapChatMessageHistory(\n        sdk=sdk, conversation_id=session_id, user_id=\"alice\",\n    ),\n)\n```\n\n### CrewAI\n\n```bash\npip install maximem-synap maximem-synap-crewai\n```\n\n```python\nfrom synap_crewai import SynapStorageBackend\n\ncrew = Crew(\n    agents=[...], tasks=[...],\n    memory=True,\n    storage=SynapStorageBackend(sdk=sdk, user_id=\"alice\"),\n)\n```\n\n### LlamaIndex\n\n```bash\npip install maximem-synap maximem-synap-llamaindex\n```\n\n```python\nfrom synap_llamaindex import SynapChatMemory\n\nmemory = SynapChatMemory(sdk=sdk, user_id=\"alice\")\nagent = ReActAgent.from_tools(tools, memory=memory)\n```\n\n### All integrations\n\n<!-- BEGIN integrations (generated by scripts/gen_readme_integrations.py) -->\n\n| Framework | Package | Install |\n|---|---|---|\n| LangChain | [`maximem-synap-langchain`](packages/integrations/synap-langchain/) | `pip install maximem-synap-langchain` |\n| LangGraph | [`maximem-synap-langgraph`](packages/integrations/synap-langgraph/) | `pip install maximem-synap-langgraph` |\n| LlamaIndex | [`maximem-synap-llamaindex`](packages/integrations/synap-llamaindex/) | `pip install maximem-synap-llamaindex` |\n| CrewAI | [`maximem-synap-crewai`](packages/integrations/synap-crewai/) | `pip install maximem-synap-crewai` |\n| AutoGen | [`maximem-synap-autogen`](packages/integrations/synap-autogen/) | `pip install maximem-synap-autogen` |\n| Haystack | [`maximem-synap-haystack`](packages/integrations/synap-haystack/) | `pip install maximem-synap-haystack` |\n| Google ADK | [`maximem-synap-google-adk`](packages/integrations/synap-google-adk/) | `pip install maximem-synap-google-adk` |\n| OpenAI Agents SDK | [`maximem-synap-openai-agents`](packages/integrations/synap-openai-agents/) | `pip install maximem-synap-openai-agents` |\n| Semantic Kernel | [`maximem-synap-semantic-kernel`](packages/integrations/synap-semantic-kernel/) | `pip install maximem-synap-semantic-kernel` |\n| Pydantic AI | [`maximem-synap-pydantic-ai`](packages/integrations/synap-pydantic-ai/) | `pip install maximem-synap-pydantic-ai` |\n| Agno | [`maximem-synap-agno`](packages/integrations/synap-agno/) | `pip install maximem-synap-agno` |\n| LiveKit Agents | [`maximem-synap-livekit-agents`](packages/integrations/synap-livekit-agents/) | `pip install maximem-synap-livekit-agents` |\n| Pipecat | [`maximem-synap-pipecat`](packages/integrations/synap-pipecat/) | `pip install maximem-synap-pipecat` |\n| Claude Agent (Python) | [`maximem-synap-claude-agent`](packages/integrations/synap-claude-agent/) | `pip install maximem-synap-claude-agent` |\n| Claude Agent (TypeScript) | [`@maximem/synap-claude-agent`](packages/integrations/synap-claude-agent-ts/) | `npm i @maximem/synap-claude-agent` |\n| Mastra | [`@maximem/synap-mastra`](packages/integrations/synap-mastra/) | `npm i @maximem/synap-mastra` |\n| Vercel AI SDK | [`@maximem/synap-vercel-adk`](packages/integrations/synap-vercel-adk/) | `npm i @maximem/synap-vercel-adk` |\n| Vercel eve | [`@maximem/synap-eve`](packages/integrations/synap-eve/) | `npm i @maximem/synap-eve` |\n| NVIDIA NeMo Agent Toolkit | [`maximem-synap-nemo-agent-toolkit`](packages/integrations/synap-nemo-agent-toolkit/) | `pip install maximem-synap-nemo-agent-toolkit` |\n| Microsoft Agent Framework | [`maximem-synap-microsoft-agent`](packages/integrations/synap-microsoft-agent/) | `pip install maximem-synap-microsoft-agent` |\n| Strands Agents | [`maximem-synap-strands-agents`](packages/integrations/synap-strands-agents/) | `pip install maximem-synap-strands-agents` |\n| CAMEL-AI | [`maximem-synap-camel-ai`](packages/integrations/synap-camel-ai/) | `pip install maximem-synap-camel-ai` |\n| Smolagents | [`maximem-synap-smolagents`](packages/integrations/synap-smolagents/) | `pip install maximem-synap-smolagents` |\n| Deepagents | [`maximem-synap-deepagents`](packages/integrations/synap-deepagents/) | `pip install maximem-synap-deepagents` |\n\n<!-- END integrations -->\n\n---\n\n## MCP server\n\nGive **no-code and low-code agents** (Gumloop, n8n, and any MCP-compatible client) persistent memory with nothing but an MCP URL and your Synap API key. No SDK, no code. The server exposes Synap's memory as three MCP tools (`log_exchange`, `recall_context`, `list_recent_memories`) over Streamable HTTP.\n\nIt's a **stateless adapter** over the hosted Synap API: each call maps to one REST operation and your Bearer token is forwarded verbatim, so there's no separate backend to run. Use the managed endpoint (grab the URL and token from your [dashboard](https://synap.maximem.ai)), or self-host the adapter from source.\n\n→ Source & self-hosting: [`packages/mcps/synap-mcp-server/`](packages/mcps/synap-mcp-server/)\n\n---\n\n## Deep dives\n\nUnderstand the system before building on it:\n\n- 📘 **[Why we built Synap](https://www.maximem.ai/blog/why-we-built-synap)**: the problem with current AI memory systems\n- ⚙️ **[How Synap works under the hood](https://www.maximem.ai/blog/how-maximem-synap-works)**: architecture, retrieval pipeline, and design decisions\n- 📊 **[Benchmark results](https://www.maximem.ai/blog/synap-benchmark-results)**: 92% on LongMemEval, 93.2% on LoCoMo, methodology, and reproducibility\n- 🧪 **[Evaluation harness](https://github.com/maximem-ai/memory_and_context_eval_harness)**: run LoCoMo and LongMemEval yourself against Synap, Mem0, Zep and Supermemory\n\n---\n\n## Agent skills\n\nDrop-in instructions for coding agents (Claude Code, Cursor, etc.) that teach them how to wire Synap into your codebase.\n\n- **[Maximem Synap skill](skills/synap/)**: covers SDK setup, scoping (User/Customer/Client), ingestion, retrieval, and one-page wiring guides for all supported frameworks.\n\n---\n\n## Requirements\n\n- **Python SDK**: Python 3.11+\n- **JavaScript SDK**: Node 18+ (Python 3.11+ for the bridge layer)\n- A Synap API key: [get one at maximem.ai](https://www.maximem.ai/synap)\n\n---\n\n## Resources & community\n\n- 📖 [Documentation](https://docs.maximem.ai)\n- 🚀 [Dashboard](https://synap.maximem.ai)\n- 𝕏 [Twitter / X](https://x.com/maximem_ai)\n- 💼 [LinkedIn](https://www.linkedin.com/company/maximem-ai)\n\n---\n\n## Contributing\n\nThis repo is a published mirror of Maximem's monorepo, so everything under `packages/` is overwritten on each sync and pull requests against it are closed. Bug reports, gaps, and new-framework requests are very welcome as [issues](https://github.com/maximem-ai/maximem_synap_sdk/issues). See [CONTRIBUTING.md](CONTRIBUTING.md) for how to run the code locally and what a new integration needs.\n\n---\n\n## License\n\nApache 2.0. See [LICENSE](LICENSE).\n\n---\n\n<p align=\"center\">\n  Built by <a href=\"https://www.maximem.ai\"><strong>Maximem AI</strong></a>\n</p>\n",
  "bytes": 14699,
  "sha": "0782e41a138f8adde9820a7565675d34eb02158d6a0e1f3a6d10aff4c2bbf286",
  "repo_slug": "maximem-ai/maximem_synap_sdk",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_maximem_synap_cf63cd15/readme"
}